/common/libraries/plugin/lastrss/lastrss.class.php
PHP | 354 lines | 236 code | 37 blank | 81 comment | 41 complexity | 4214b9d96ba4f01e994ddcabea7659ce MD5 | raw file
Possible License(s): GPL-2.0, BSD-3-Clause, LGPL-2.1, LGPL-3.0, GPL-3.0, MIT
- <?php
- /*
- ======================================================================
- lastRSS 0.9.1
-
- Simple yet powerfull PHP class to parse RSS files.
-
- by Vojtech Semecky, webmaster @ webdot . cz
-
- Latest version, features, manual and examples:
- http://lastrss.oslab.net/
- ----------------------------------------------------------------------
- LICENSE
- This program is free software; you can redistribute it and/or
- modify it under the terms of the GNU General Public License (GPL)
- as published by the Free Software Foundation; either version 2
- of the License, or (at your option) any later version.
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- GNU General Public License for more details.
- To read the license please visit http://www.gnu.org/copyleft/gpl.html
- ======================================================================
- */
- /**
- * lastRSS
- * Simple yet powerfull PHP class to parse RSS files.
- */
- class LastRss
- {
- // TODO: Implement PEAR RSS parser package
- private $default_cp = 'UTF-8';
- private $cdata;
- private $cp;
- private $items_limit;
- private $strip_html;
- private $date_format;
- private $cache_dir;
- private $cache_time;
-
- private $feed_url;
-
- private $channeltags = array ('title', 'link', 'description', 'language', 'copyright', 'managingEditor', 'webMaster', 'lastBuildDate', 'rating', 'docs');
- private $itemtags = array('title', 'link', 'description', 'author', 'category', 'comments', 'enclosure', 'guid', 'pubDate', 'source');
- private $imagetags = array('title', 'url', 'link', 'width', 'height');
- private $textinputtags = array('title', 'description', 'name', 'link');
-
- function __construct($url)
- {
- // Set default values, can be overwritten via setters if necessary
- $this->cdata = 'content';
- $this->cp = 'UTF-8';
- $this->items_limit = 0;
- $this->strip_html = false;
- $this->date_format = 'd F Y, H:i:s';
-
- $this->cache_dir = dirname(__FILE__).'/../../cache';
- // Default is 3600 seconds = 1 hour
- $this->cache_time = 3600;
-
- // Feed url as passed on from the module
- $this->feed_url = $url;
- }
-
- function get_default_cp()
- {
- return $this->default_cp;
- }
-
- function get_cdata()
- {
- return $this->cdata;
- }
-
- function get_cp()
- {
- return $this->cp;
- }
-
- function get_items_limit()
- {
- return $this->items_limit;
- }
-
- function get_strip_html()
- {
- return $this->strip_html;
- }
-
- function get_date_format()
- {
- return $this->date_format;
- }
-
- function get_cache_dir()
- {
- return $this->cache_dir;
- }
-
- function get_cache_time()
- {
- return $this->cache_time;
- }
-
- function get_feed_url()
- {
- return $this->feed_url;
- }
-
- function set_default_cp($default_cp)
- {
- $this->default_cp = $default_cp;
- }
-
- function set_cdata($cdata)
- {
- $this->cdata =$cdata ;
- }
-
- function set_cp($cp)
- {
- $this->cp = $cp;
- }
-
- function set_items_limit($items_limit)
- {
- $this->items_limit = $items_limit;
- }
-
- function set_strip_html($strip_html)
- {
- $this->strip_html = $strip_html;
- }
-
- function set_date_format($date_format)
- {
- $this->date_format = $date_format;
- }
-
- function set_feed_url($feed_url)
- {
- $this->feed_url = $feed_url;
- }
-
- function set_cache_dir($cache_dir)
- {
- $this->cache_dir = $cache_dir;
- }
-
- function set_cache_time($cache_time)
- {
- $this->cache_time = $cache_time;
- }
- // -------------------------------------------------------------------
- // Parse RSS file and returns associative array.
- // -------------------------------------------------------------------
- function get_feed_content()
- {
- // If CACHE ENABLED
- if ($this->cache_dir != '')
- {
- $cache_file = $this->cache_dir . '/rsscache_' . md5($this->feed_url);
- $timedif = @(time() - filemtime($cache_file));
-
- if ($timedif < $this->cache_time)
- {
- // cached file is fresh enough, return cached array
- $result = unserialize(join('', file($cache_file)));
- // set 'cached' to 1 only if cached file is correct
- if ($result) $result['cached'] = 1;
- }
- else
- {
- // cached file is too old, create new
- $result = $this->parse_feed_content();
- $serialized = serialize($result);
-
- if ($f = @fopen($cache_file, 'w'))
- {
- fwrite ($f, $serialized, strlen($serialized));
- fclose($f);
- }
-
- if ($result) $result['cached'] = 0;
- }
- }
- // If CACHE DISABLED >> load and parse the file directly
- else
- {
- $result = $this->parse_feed_content();
- if ($result) $result['cached'] = 0;
- }
- // return result
- return $result;
- }
-
- // -------------------------------------------------------------------
- // Modification of preg_match(); return trimed field with index 1
- // from 'classic' preg_match() array output
- // -------------------------------------------------------------------
- function my_preg_match ($pattern, $subject) {
- // start regullar expression
- preg_match($pattern, $subject, $out);
- // if there is some result... process it and return it
- if(isset($out[1]))
- {
- // Process CDATA (if present)
- if ($this->cdata == 'content')
- {
- // Get CDATA content (without CDATA tag)
- $out[1] = strtr($out[1], array('<![CDATA['=>'', ']]>'=>''));
- }
- elseif ($this->cdata == 'strip')
- {
- // Strip CDATA
- $out[1] = strtr($out[1], array('<![CDATA['=>'', ']]>'=>''));
- }
- // If code page is set convert character encoding to required
- if ($this->cp != '') $out[1] = iconv($this->rsscp, $this->cp.'//TRANSLIT', $out[1]);
- // Return result
- return trim($out[1]);
- }
- else
- {
- // if there is NO result, return empty string
- return '';
- }
- }
- // -------------------------------------------------------------------
- // Replace HTML entities &something; by real characters
- // -------------------------------------------------------------------
- private function unhtmlentities ($string)
- {
- // Get HTML entities table
- $trans_tbl = get_html_translation_table (HTML_ENTITIES, ENT_QUOTES);
- // Flip keys<==>values
- $trans_tbl = array_flip ($trans_tbl);
- // Add support for ' entity (missing in HTML_ENTITIES)
- $trans_tbl += array(''' => "'");
- // Replace entities by values
- return strtr ($string, $trans_tbl);
- }
- // -------------------------------------------------------------------
- // Parse() is private method used by Get() to load and parse RSS file.
- // Don't use Parse() in your scripts - use Get($rss_file) instead.
- // -------------------------------------------------------------------
- private function parse_feed_content()
- {
- // Open and load RSS file
- if ($f = @fopen($this->feed_url, 'r'))
- {
- $rss_content = '';
- while (!feof($f))
- {
- $rss_content .= fgets($f, 4096);
- }
- fclose($f);
- // Parse document encoding
- $result['encoding'] = $this->my_preg_match("'encoding=[\'\"](.*?)[\'\"]'si", $rss_content);
- // if document codepage is specified, use it
- if ($result['encoding'] != '')
- { $this->rsscp = $result['encoding']; } // This is used in my_preg_match()
- // otherwise use the default codepage
- else
- { $this->rsscp = $this->default_cp; } // This is used in my_preg_match()
- // Parse CHANNEL info
- preg_match("'<channel.*?>(.*?)</channel>'si", $rss_content, $out_channel);
- foreach($this->channeltags as $channeltag)
- {
- $temp = $this->my_preg_match("'<$channeltag.*?>(.*?)</$channeltag>'si", $out_channel[1]);
- if ($temp != '') $result[$channeltag] = $temp; // Set only if not empty
- }
- // If date_format is specified and lastBuildDate is valid
- if ($this->date_format != '' && ($timestamp = strtotime($result['lastBuildDate'])) !==-1)
- {
- // convert lastBuildDate to specified date format
- $result['lastBuildDate'] = date($this->date_format, $timestamp);
- }
- // Parse TEXTINPUT info
- preg_match("'<textinput(|[^>]*[^/])>(.*?)</textinput>'si", $rss_content, $out_textinfo);
- // This a little strange regexp means:
- // Look for tag <textinput> with or without any attributes, but skip truncated version <textinput /> (it's not beggining tag)
- if (isset($out_textinfo[2]))
- {
- foreach($this->textinputtags as $textinputtag)
- {
- $temp = $this->my_preg_match("'<$textinputtag.*?>(.*?)</$textinputtag>'si", $out_textinfo[2]);
- if ($temp != '') $result['textinput_'.$textinputtag] = $temp; // Set only if not empty
- }
- }
- // Parse IMAGE info
- preg_match("'<image.*?>(.*?)</image>'si", $rss_content, $out_imageinfo);
- if (isset($out_imageinfo[1]))
- {
- foreach($this->imagetags as $imagetag)
- {
- $temp = $this->my_preg_match("'<$imagetag.*?>(.*?)</$imagetag>'si", $out_imageinfo[1]);
- if ($temp != '') $result['image_'.$imagetag] = $temp; // Set only if not empty
- }
- }
- // Parse ITEMS
- preg_match_all("'<item(| .*?)>(.*?)</item>'si", $rss_content, $items);
- $rss_items = $items[2];
- $i = 0;
- $result['items'] = array(); // create array even if there are no items
- foreach($rss_items as $rss_item)
- {
- // If number of items is lower then limit: Parse one item
- if ($i < $this->items_limit || $this->items_limit == 0)
- {
- foreach($this->itemtags as $itemtag) {
- $temp = $this->my_preg_match("'<$itemtag.*?>(.*?)</$itemtag>'si", $rss_item);
- if ($temp != '') $result['items'][$i][$itemtag] = $temp; // Set only if not empty
- }
- // Strip HTML tags and other bullshit from DESCRIPTION
- if ($this->strip_html && $result['items'][$i]['description'])
- $result['items'][$i]['description'] = strip_tags($this->unhtmlentities(strip_tags($result['items'][$i]['description'])));
- // Strip HTML tags and other bullshit from TITLE
- if ($this->strip_html && $result['items'][$i]['title'])
- $result['items'][$i]['title'] = strip_tags($this->unhtmlentities(strip_tags($result['items'][$i]['title'])));
- // If date_format is specified and pubDate is valid
- if ($this->date_format != '' && ($timestamp = strtotime($result['items'][$i]['pubDate'])) !==-1) {
- // convert pubDate to specified date format
- $result['items'][$i]['pubDate'] = date($this->date_format, $timestamp);
- }
- // Item counter
- $i++;
- }
- }
- $result['items_count'] = $i;
- return $result;
- }
- else // Error in opening return False
- {
- return False;
- }
- }
- }
- ?>